A clearer view of Earth’s water cycle via neural networks and satellite data

Larson, Albert

doi:10.1038/s43017-022-00303-x

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…https://doi.org/10.1038/s44221-023-00069-6 patterns 19 . This includes quantity parameters, such as evapotranspiration 20 , condensation, precipitation 21 , infiltration, surface run-off, streamflow 22 , subsurface flow and soil moisture 23 , as well as quality factors, for example, nutrients such as phosphorus and nitrogen 24 and minerals such as flouride 25 .…”

Section: Perspectivementioning

confidence: 99%

Rewards, risks and responsible deployment of artificial intelligence in water systems

et al. 2023

View full text Add to dashboard Cite

Section: Perspectivementioning

confidence: 99%

Rewards, risks and responsible deployment of artificial intelligence in water systems

et al. 2023

View full text Add to dashboard Cite

“…Creating easy to use tools for modeling, management, and risk communication such as in Ref. [58] opens this field to researchers who may not otherwise have the skill or knowledge to do work with remote sensing data. For example, ref.…”

Section: Remote Sensing In Water Quality Applicationsmentioning

confidence: 99%

“…For example, ref. [58] developed an easy-to-use open-source neural network framework for modeling high resolution water quality and quantity changes based on radiometer observations of water flux forcings.…”

Section: Remote Sensing In Water Quality Applicationsmentioning

confidence: 99%

Water Quality Observations from Space: A Review of Critical Issues and Challenges

et al. 2022

Self Cite

View full text Add to dashboard Cite

Water is the basis of all life on this planet. Yet, approximately one in seven people in the world do not have access to safe water. Water can become unsafe due to contamination by various organic and inorganic compounds due to various natural and anthropogenic processes. Identifying and monitoring water quality changes in space and time remains a challenge, especially when contamination events occur over large geographic areas. This study investigates recent advances in remote sensing that allow us to detect and monitor the unique spectral characteristics of water quality events over large areas. Based on an extensive literature review, we focus on three critical water quality problems as part of this study: algal blooms, acid mine drainage, and suspended solids. We review the advances made in applications of remote sensing in each of these issues, identify the knowledge gaps and limitations of current studies, analyze the existing approaches in the context of global environmental changes, and discuss potential ways to combine multi-sensor methods and different wavelengths to develop improved approaches. Synthesizing the findings of these studies in the context of the three specific tracks will help stakeholders to utilize, share, and embed satellite-derived earth observations for monitoring and tracking the ever-evolving water quality in the earth’s limited freshwater reserves.

show abstract

“…Nvidia has just crossed the trillion dollar market capitalization in large part to the AI boom driven by the proliferation of generative models like GPT and Stable Diffusion [26]. Here, we build on an existing neural network architecture called dcrrnn, which stands for a deep convolutional residual regressive neural network and is pronounced "discern" [27,28]. When applied to problems involving the water cycle, dcrrnn is under the umbrella of Flux to Flow (F2F).…”

Section: Introductionmentioning

confidence: 99%

Discerning Watershed Response to Hydroclimatic Extremes with a Deep Convolutional Residual Regressive Neural Network

et al. 2023

Self Cite

View full text Add to dashboard Cite

The impact of climate change continues to manifest itself daily in the form of extreme events and conditions such as droughts, floods, heatwaves, and storms. Better forecasting tools are mandatory to calibrate our response to these hazards and help adapt to the planet’s dynamic environment. Here, we present a deep convolutional residual regressive neural network (dcrrnn) platform called Flux to Flow (F2F) for discerning the response of watersheds to water-cycle fluxes and their extremes. We examine four United States drainage basins of varying acreage from smaller to very large (Bear, Colorado, Connecticut, and Mississippi). F2F combines model and ground observations of water-cycle fluxes in the form of surface runoff, subsurface baseflow, and gauged streamflow. We use these time series datasets to simulate, visualize, and analyze the watershed basin response to the varying climates and magnitudes of hydroclimatic fluxes in each river basin. Experiments modulating the time lag between remotely sensed and ground-truth measurements are performed to assess the metrological limits of forecasting with this platform. The resultant mean Nash–Sutcliffe and Kling–Gupta efficiency values are both greater than 90%. Our results show that a hydrological machine learning platform such as F2F can become a powerful resource to simulate and forecast hydroclimatic extremes and the resulting watershed responses and natural hazards in a changing global climate.

show abstract

A clearer view of Earth’s water cycle via neural networks and satellite data

Cited by 3 publications

References 0 publications

Rewards, risks and responsible deployment of artificial intelligence in water systems

Rewards, risks and responsible deployment of artificial intelligence in water systems

Water Quality Observations from Space: A Review of Critical Issues and Challenges

Discerning Watershed Response to Hydroclimatic Extremes with a Deep Convolutional Residual Regressive Neural Network

Contact Info

Product

Resources

About